By Topic

Optimal Genetic Fuzzy Obstacle Avoidance Controller of Autonomous Mobile Robot Based on Ultrasonic Sensors

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Qiao Liu ; Electr. & Inf. Eng. Coll., Changsha Univ. of Sci. & Technol., Changsha ; Yong-gang Lu ; Cun-xi Xie

In order to avoid obstacles efficiently and reach the goal quickly under multi-obstacle environment, we studied the path planning question of autonomous mobile robot (AMR) based on ultrasonic sensor information by combining genetic algorithm with fuzzy logic control. Firstly, the principles and configuration of ultrasonic sensors were introduced. Secondly, the dynamic model and kinetic equations of AMR were constructed. Then, according to the number of obstacles, the avoiding behavior and rules were presented, moreover, the obstacle-selecting and avoidance rules and flow chart of AMR under multi-obstacles environment were also proposed. Based on above, we designed a fuzzy controller to modify the moving direction of AMR by defining or establishing input variables, output variables, fuzzy membership functions, fuzzy rule base including 25 If-Then fuzzy inference rules and defuzzification method. At last, a genetic algorithm was added for optimal searching parameters which includes the 5 times 5 consequent variables of the control rule table, the searching parameters, the bottom parameters of triangular membership functions and scaling factors. By setting the total route length as the target function, we founded the optimal genetic fuzzy controller for various obstructive environments through Matlab 6.5 simulation. The simulation results show the optimal controller under obstructive environment has better adaptability and passes shorter route in complex environment.

Published in:

Robotics and Biomimetics, 2006. ROBIO '06. IEEE International Conference on

Date of Conference:

17-20 Dec. 2006